Note where the AD tools are going: DifferentialEquations - Derivatives in ODE function/ nesting AD - #2 by ChrisRackauckas . I think most of these issues should be handled by what we’re moving things towards.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Tracking initial condition to optimize starting value too Diffeqflux | 11 | 1350 | July 25, 2019 | |
| Neural Networks combined with Diffeq | 26 | 1395 | May 7, 2021 | |
| DifferentialEquations.jl + Flux.jl or Knet.jl | 15 | 3649 | October 18, 2018 | |
| Different loss function for training ODE or DDE? | 5 | 604 | January 20, 2021 | |
| Neural ODE fitting really slow | 13 | 2018 | September 11, 2020 |